Learning Goals from Failure

Abstract

We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct supervision. Our approach models videos as contextual trajectories that represent both low-level motion and high-level action features. Experiments and visualizations show our trained model is able to predict the underlying goals in video of unintentional action. We also propose a method to "automatically correct" unintentional action by leveraging gradient signals of our model to adjust latent trajectories. Although the model is trained with minimal supervision, it is competitive with or outperforms baselines trained on large (supervised) datasets of successfully executed goals, showing that observing unintentional action is crucial to learning about goals in video. Project page: https://aha.cs.columbia.edu/

References in corpus (7)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• A Short Note about Kinetics-600
• Self-supervised Co-training for Video Representation Learning
• Generating Steganographic Images via Adversarial Training
• The AVA-Kinetics Localized Human Actions Video Dataset
• Memory-augmented Dense Predictive Coding for Video Representation Learning
• Invisible Mask: Practical Attacks on Face Recognition with Infrared